請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98722完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 何昊哲 | zh_TW |
| dc.contributor.advisor | Hao-Che Ho | en |
| dc.contributor.author | 李漢濬 | zh_TW |
| dc.contributor.author | Han-Jun Lee | en |
| dc.date.accessioned | 2025-08-18T16:14:07Z | - |
| dc.date.available | 2025-08-19 | - |
| dc.date.copyright | 2025-08-18 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-07 | - |
| dc.identifier.citation | Abd Elbasit, M. A., Yasuda, H., & Salmi, A. (2011). Application of piezoelectric transducers in simulated rainfall erosivity assessment. Hydrological Sciences Journal, 56(1), 187–194.
Abudi, I., Carmi, G., & Berliner, P. (2012). Rainfall simulator for field runoff studies. Journal of Hydrology, 454, 76–81. Agassi, M., & Bradford, J. (1999). Methodologies for inter-rill soil erosion studies. Soil and Tillage Research, 49, 277–287. Aksoy, H., Unal, N. E., Cokgor, S., Gedikli, A., Yoon, J., Koca, K., & Eris, E. (2012). A rainfall simulator for laboratory-scale assessment of rainfall-runoff-sediment transport processes over a two-dimensional flume. Catena, 98, 63–72. Aleotti, P. (2004). A warning system for rainfall-induced shallow failures. Engineering Geology, 73(3–4), 247–265. Arkin, P. A., & Meisner, B. N. (1987). The relationship between large-scale convective rainfall and cold over the western hemisphere during 1982–1984. Monthly Weather Review, 115, 51–74. Bian, Y., Zhang, H., Wang, H., & Fu, X. (2021). Automatic river water level extraction using infrared thermal imagery and deep learning. Water Resources Management, 35(12), 3977–3990. Bospio, R., Cagninei, A., & Poggi, D. (2023). Innovative characterization and comparative analysis of water level sensors: Ultrasonic, infrared, pressure and radar-based methods. Sensors, 13(2), 26. Bradley, A. A., Kruger, A., Meselhe, E. A., & Muste, M. V. (2002). Flow measurement in streams using video imagery. Water Resources Research, 38(12), 51-1–51-8. Chen, R., Li, W., & Xu, Z. (2019). A novel radar-based water level monitoring system for urban flooding. IEEE Sensors Journal, 19(15), 5862–5870. Chuang, Y.-J., & Chan, H.-C. (2018). Measurements of flow velocity by using LSPIV with UAV in different flow conditions. AGU Fall Meeting Abstracts, H43Q–1747. Ciach, G. J., Krajewski, W. F., & Kruger, A. (2003). Local random errors in tipping-bucket rain gauge measurements. Journal of Atmospheric and Oceanic Technology, 20(5), 752–759. Coudray, N., Ocampo, P. S., Sakellaropoulos, T., Narula, N., Snuderl, M., Fenyo, D., Moreira, A. L., Razavian, N., & Tsirigos, A. (2018). Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nature Medicine, 24(10), 1559–1567. Deng, C., Sun, K., Wang, J., Zhang, Z., & Wang, Y. (2020). A deep learning framework for water level detection in rivers using surveillance video. IEEE Transactions on Geoscience and Remote Sensing, 58(11), 8200–8212. Erpul, G., Norton, L. D., & Gabriels, D. (2003). Sediment transport from interrill areas under wind-driven rain. Journal of Hydrology, 276(1–4), 184–197. Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2012). Scene parsing with multiscale feature learning, purity trees, and optimal covers. International Conference on Machine Learning (ICML), 575–582. Fleury, D. J., do Nascimento, D. V., Galvão Filho, A. R., Ribeiro, F. d. S. L., de Carvalho, R. V., & Coelho, C. J. (2020). Image-based river water level estimation for redundancy information using deep neural network. Energies, 13(24), 6706. Fujita, I., & Komura, S. (1994). Application of video image analysis for measurements of river-surface flows. Proceedings of Hydraulic Engineering, 38, 733–738. Fujita, I., Muste, M., & Kruger, A. (1998). Large-scale particle image velocimetry for flow analysis in hydraulic engineering applications. Journal of Hydraulic Research, 36(3), 397–414. Galli, A., Peruzzi, C., Gangi, F., & Masseroni, D. (2024). ArduHydro: A low cost device for water level measurement and monitoring. Journal of Agricultural Engineering, 55(1), Article 1554. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 580–587. Govers, G. (1991). Rill erosion on arable land in central Belgium: Rates, controls and predictability. Catena, 18, 133–155. Guillén, N. F., Patalano, A., García, C. M., & Bertoni, J. C. (2017). Use of LSPIV in assessing urban flash flood vulnerability. Natural Hazards, 87(1), 383–394. Guo, X., Zhang, C., & Wang, Y. (2020). A vision-based water level measurement approach using improved edge detection and template matching. Water Science and Technology: Water Supply, 20(8), 3187–3197. Habib, E., Krajewski, W. F., & Kruger, A. (2003). Sampling errors of tipping-bucket rain gauge measurements. Journal of Hydrologic Engineering, 8(6), 388–395. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. IEEE CVPR, 770–778. Imeson, A. C., & Kwaad, F. J. P. M. (1990). The response of tilled soils to wetting by rainfall and the dynamic character of soil crusting. Soil and Tillage Research, 17(1–2), 39–53. Jiang, B., Sun, Z., Liu, S., & Peng, H. (2021). Water level measurement based on video images and frequency domain analysis. Measurement Science and Technology, 32(11), 115010. Kim, Y. (2006). Uncertainty analysis for non-intrusive measurement of river discharge using image velocimetry. Ph.D. Dissertation, The University of Iowa. Kokkinos, I. (2016). UberNet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6129–6138. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems (NIPS), 25, 1097–1105. Kruger, A., Habib, E., & Krajewski, W. F. (1998). Influence of systematic errors from tipping bucket rain gauges on hydrological applications. Journal of Hydrology, 209(1–4), 282–290. Lazebnik, S., Schmid, C., & Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. IEEE CVPR, 2, 2169–2178. Le, H. (2011). Face recognition using convolutional neural networks. University of Toronto Thesis. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. Lewis, Q. W., Lindroth, E. M., & Rhoads, B. L. (2018). Integrating unmanned aerial systems and LSPIV for rapid, cost-effective stream gauging. Journal of Hydrology, 560, 230–246. Li, J., Li, Z., & Hu, W. (2022). Enhancing water level detection accuracy using generative adversarial networks. Sensors, 22(9), 3467. Lin, F., Chang, W. Y., Lee, L. C., Hsiao, H. T., Tsai, W. F., & Lai, J. S. (2013, December). Applications of image recognition for real-time water level and surface velocity. Proceedings of the 35th Asian Conference on Remote Sensing (ACRS), Bali, Indonesia. Lin, Y. T., Lin, Y. C., & Han, J. Y. (2018). Automatic water-level detection using camera images with varied poses. IEEE Sensors Journal, 18(6), 2501–2509. Liu, B. Y., Nearing, M. A., & Stone, J. J. (1994). A double-ring infiltrometer for measuring hydraulic conductivity of surface soil crust. Soil Science Society of America Journal, 58(2), 542–545. Lu, Y., Yang, S., Chen, Q., & Zhao, H. (2022). A computer vision-based method for water level monitoring using deep learning and edge detection. Sensors, 22(14), 5132. Marr, D., & Poggio, T. (1976). A cooperative computation of stereo disparity. Science, 194(4262), 283–287. Mikuš, P., & Harťanský, R. (2013). The errors in radar level gauge calibration. Measurement, 46(10), 4040–4044. Muste, M., Yu, K., & Spasojevic, M. (2004). Practical aspects of ADCP data use for quantification of mean river flow characteristics; Part I: Moving-vessel measurements. Flow Measurement and Instrumentation, 15(1), 1–16. Nascimento, D. V. (2021). Automatic measurement of river water-level using image computer vision. Master’s Thesis, Federal University of Pernambuco, Brazil. Natividad, J., & Mendez, J. (2018). Flood monitoring and early warning system using ultrasonic sensor. IOP Conference Series: Materials Science and Engineering, 325, 012014. Nearing, M. A., Norton, L. D., Bulgakov, D. A., Larionov, G. A., West, L. T., & Dontsova, K. (1997). Hydraulics and erosion in eroding rills. Water Resources Research, 33(4), 865–876. Ning, H., Xu, W., Huang, Y., & Huang, T. S. (2005). Toward automatic phenotyping of developing embryos using multispectral confocal images. Proceedings of the IEEE, 93(5), 883–898. Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62–66. Planchon, O., & Darboux, F. (2001). A fast, simple and versatile algorithm to fill the depressions of digital elevation models. Catena, 46(2–3), 159–176. Renard, K. G., Foster, G. R., Weesies, G. A., McCool, D. K., & Yoder, D. C. (1997). Predicting soil erosion by water: A guide to conservation planning with the Revised Universal Soil Loss Equation (RUSLE). Agriculture Handbook, 703, 1–384. Resch, F., & Leutbecher, M. (2006). Accuracy of surface water level measurements using radar altimetry. arXiv preprint, arXiv:physics/0608056. River Network. (n.d.). Water level gauge, Mississippi River, Prairie du Chien, USA. Sadeghfam, S., & Beheshti, A. (2023). A novel computer vision-based method for real-time river water level monitoring. Water, 15(1), 161. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. IEEE CVPR, 4510–4520. Segovia Cardozo, D. A., Bernal Basurco, C., & Rodríguez Sinobas, L. (2023). Tipping bucket rain gauges in hydrological research: Summary on measurement uncertainties, calibration, and error reduction strategies. Sensors, 23(12), 5385. Shailaja, S., & Anuradha, J. (2016). Face recognition using CNN: A survey. International Journal of Engineering and Techniques, 2(6), 56–59. Shelley Signs. (n.d.). Gauge boards for water depths. Shi, C., Ma, Z., & Huang, J. (2020). Accurate water level detection method based on video monitoring and edge segmentation. IEEE Access, 8, 186791–186800. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. Song, K., Liu, F., Xu, J., & Zhang, X. (2021). Waterline extraction from river images using U-Net based semantic segmentation. Journal of Hydrology, 598, 126336. Statista. (2023). Number of natural disasters worldwide from 2000 to 2022. Tan, Y., Zhang, B., & Wu, Q. (2018). Vision-based real-time water level monitoring system for river management. Environmental Monitoring and Assessment, 190(7), 392. Tauro, F., Pagano, C., Phamduy, P., Grimaldi, S., & Porfiri, M. (2015). Large-scale particle image velocimetry from an unmanned aerial vehicle. IEEE/ASME Transactions on Mechatronics, 20(6), 3269–3275. Tourian, M. J., Elmi, O., Chen, Q., Devaraju, B., Roohi, S., & Sneeuw, N. (2016). A spaceborne multisensor approach to monitor the desiccation of Lake Urmia in Iran. Remote Sensing of Environment, 160, 66–78. United Nations Office for Disaster Risk Reduction (UNDRR). (2020). Human cost of disasters: An overview of the last 20 years (2000–2019). United Nations Office for Disaster Risk Reduction. Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., & Xiao, B. (2020). Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10), 3349–3364. Wang, S., Liu, Y., & Yang, Q. (2021). River water level monitoring using UAV images and deep learning. Remote Sensing, 13(24), 5068. Wu, J. H., Tseng, C. H., Chen, L. C., Lo, S. W., & Lin, F. P. (2015, June). Automated image identification method for flood disaster monitoring in riverine environments: A case study in Taiwan. 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2657–2660. Wu, Y., Yu, D., & Cao, Y. (2022). River level measurement based on YOLOv5 and improved Hough transform. Water, 14(9), 1461. Wu, Z., Huang, Y., Huang, K., Yan, K., & Chen, H. (2023). A review of non contact water level measurement based on computer vision and radar technology. Water, 15(18), 3233. Yang, J., Zhang, Y., Wang, L., & Wu, H. (2022). Water level detection in complex environments based on improved CNN regression. Applied Sciences, 12(6), 2842. Yin, H., Li, Z., Wang, Y., & Xie, Y. (2023). Intelligent monitoring of reservoir water levels using an improved deep learning model. Remote Sensing, 15(3), 587. Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., & Sang, N. (2021). Lite-HRNet: A lightweight high-resolution network. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 10440–10450. Yu, J., & Hahn, H. (2010). Remote detection and monitoring of a water level using narrow band channel. Journal of Electrical Engineering & Technology, 5(1), 148–153. Yuan, Y., Wang, R., Wang, J., et al. (2024). A deep learning-based method for water surface detection using multi-source data. Scientific Reports, 14, Article 6704. Zhang, D., & Tong, J. (2023). Robust water level measurement method based on computer vision. Hikvision Digital Technology Company Limited. Zhang, J., Yang, Y., & Su, H. (2018). Crack detection in cement pavement based on convolutional neural network. Neural Computing and Applications, 32, 10789–10798. Zhang, Y., Sun, D., Wang, H., & Dong, G. (2021). Monitoring the sea surface current with an artificial intelligent high-frequency radar data processing system. Frontiers in Marine Science, 8, 679323. Zhang, Z., Wang, X., Fan, T., & Xu, L. (2013). River surface target enhancement and background suppression for unseeded LSPIV. Flow Measurement and Instrumentation, 30, 99–111. Zhang, Z., Zhang, X., Peng, C., Cheng, D., & Sun, J. (2018). ExFuse: Enhancing Feature Fusion for Semantic Segmentation. arXiv preprint arXiv:1804.03821. Zhang, Z., Zhou, Y., Liu, H., & Gao, H. (2019). In-situ water level measurement using N imaging video camera. Measurement, 147, 106879. Zhao, X., Zhu, Y., & Fang, C. (2020). Water level detection based on object detection and image processing. International Journal of Environmental Research and Public Health, 17(21), 8026. Zhen, H., Wang, L., & Zhao, Z. (2019). Visual measurement of water level under complex illumination conditions. Sensors, 19(18), 4141. 水利署水文資訊整合平台(2024).河川水位開放資料查詢. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98722 | - |
| dc.description.abstract | 隨著氣候變遷導致極端降雨頻率增加，河川水位監測在水利防災中扮演愈加關鍵的角色。然而，傳統水位監測方式多依賴實體水尺與人工判讀，不僅在偏遠地區佈建困難，也容易受環境因素干擾而降低辨識準確度。為解決此問題，本研究提出一套結合電腦視覺與虛擬水尺的自動水位量測方法，透過深度學習模型自動辨識影像中的水面線，並轉換為實際水位高度資訊。
本研究採用 High-Resolution Network (HRNET)架構進行水面線位置的回歸訓練，設計並輸出 20 個等間距的垂直坐標。訓練資料來源涵蓋實地攝影與實驗水槽影像，並搭配人工標註進行模型訓練。為提升模型辨識能力，本研究設計資料擴增策略，包括外觀變化擴增（ADA）與方向性隨機擴展（RED），並透過困難樣本補強與劣質樣本剔除來優化訓練資料集，解決模型訓練錯誤與誤判問題。預測結果經由影像正射校正與虛擬水尺的轉換，可準確換算成水位高程。後處理方面，則引入多張影像時間平均與傅立葉分析，提升輸出穩定性與應用可靠度。 實驗結果顯示，最終模型的平均絕對誤差（MAE）為 0.0157，決定係數（R²）達 0.9874，在 2% 誤差容忍度下準確率為 84.97%，10% 誤差容忍度下準確率達 99.5%。本研究所建構系統在多樣化的影像情境下具備良好的水面線辨識與水位估算能力，並於特定誤差範圍內達成高準確率。本研究不僅展示深度學習模型應用於無水尺環境下水位判讀之可行性，也證明透過樣本資料優化與後處理設計，能有效提升系統於實務應用中的穩定性，為智慧型水文監測提供新的技術方向。 | zh_TW |
| dc.description.abstract | With the increasing frequency of extreme rainfall events driven by climate change, river water level monitoring has become a critical component of disaster prevention and water resource management. However, conventional methods relying on physical staff gauges and manual interpretation face challenges in installation, accuracy, and efficiency, especially in remote or harsh environments. To address these limitations, this study proposes an automated water level measurement system integrating computer vision and virtual gauge technology.
The system employs a deep learning model based on the High-Resolution Network (HRNet) architecture to detect the water surface line in images and convert the output into actual water level estimations. The model performs a regression task by predicting the vertical coordinates of 20 equally spaced points along the water surface. The model is trained on images from field sites and laboratory flumes, with manually labeled ground truth. To enhance model robustness, data augmentation strategies, including Appearance-based Data Augmentation (ADA) and Random Extension in Direction (RED), are introduced along with difficult sample supplementation and poor-quality sample removal for dataset optimization. Predicted results are orthorectified and mapped to virtual gauge elevations, and further stabilized using multi-frame averaging and Fourier-based wave analysis. Experimental results demonstrate that the proposed system achieves exceptional accuracy with a Mean Absolute Error (MAE) of 0.0157, coefficient of determination (R²) of 0.9874, accuracy rates of 84.97% at 2% error tolerance and 99.5% at 10% error tolerance. The system performs reliably under diverse environmental conditions without requiring physical water gauges. This study validates the feasibility of applying deep learning to automated water level estimation in natural environments and highlights the value of dataset optimization and post-processing in enhancing reliability and field applicability. The research provides a novel technical approach for intelligent hydrological monitoring systems. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-08-18T16:14:07Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-08-18T16:14:07Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 I
摘要 II ABSTRACT III 目 次 V 圖 次 X 表 次 XIV 第一章 緒論 1 1.1 研究動機 1 1.2 研究目的與流程 3 1.3 論文研究架構 5 第二章 文獻回顧 6 2.1 傳統水位量測技術 6 2.1.1 實體水尺與人工觀測法 7 2.1.2 壓力式水位計 9 2.1.3 超音波水位計 11 2.1.4 雷達水位計 13 2.2 影像辨識方法 15 2.2.1 可見光影像式水位辨識方法 15 2.2.2 紅外線熱影像水位辨識 15 2.2.3 衛星遙測水位推估 16 2.2.4 方法選擇 16 2.3 影像式水位辨識方法發展與挑戰 16 2.4 深層CNN於邊界辨識任務的侷限 18 2.5 自然背景下的水位判讀挑戰 20 2.6 研究目標 22 第三章 研究方法 23 3.1 資料來源與水位標記 23 3.1.1 影像資料-模擬影像 23 3.1.2 影像資料-真實影像 24 3.1.3 水位影像前處理 26 3.1.4 水面線標注 28 3.2 HRNET 模型架構選擇與訓練設置 29 3.2.1 卷積神經網絡 29 3.2.2 HRNet（High-Resolution Network） 30 3.2.3 HRNet模型版本比較 31 3.2.4 回歸任務 34 3.2.5 Smooth L1 Loss 損失函數 34 3.3 訓練樣本集優化與擴增 35 3.3.1 Appearance-based Data Augmentation（外觀擴增） 35 3.3.2 Random Extension in Direction（方向性隨機擴展） 37 3.3.3 困難樣本比例補強 38 3.4 模型效能評估指標與驗證方式 40 3.4.1 MAE、RMSE、R² 評估 41 3.4.2 分級準確率 ACC 41 3.4.3 成果判斷 42 3.5 虛擬水尺與影像正射校正 42 3.5.1 攝影機設置與校正流程 42 3.5.2 正射校正與H矩陣計算方式 43 3.5.3 虛擬水尺刻度生成與高程對應關係 45 3.6 預測結果轉換與後處理 46 3.6.1 預測坐標轉為水位高程 46 3.6.2 連續影像時間平均與雜訊抑制 46 3.6.3 水位爬升速率預警 47 第四章 研究結果與討論 50 4.1 模型訓練結果與收斂分析 50 4.1.1 Lite-HRNet模型訓練過程 51 4.1.2 HRNet-Semantic-Segmentation模型訓練過程 53 4.1.3 HRNet-Image-Classification模型訓練過程 55 4.2 預測結果視覺化與誤差案例分析 57 4.2.1 初始樣本集置中偏誤對模型訓練之影響 57 4.2.2 擴增樣本後之新誤差類型與對策調整 60 4.3 訓練樣本擴增前後之比較 66 4.3.1 水位判讀效果比較 66 4.3.2 改善程度量化 70 4.4 影像水位輸出與應用 74 4.4.1 模擬影像判讀 75 4.4.2 真實影像判讀 76 4.4.3 比較多張平均的水位曲線變化 77 4.4.4 傅立葉轉換頻譜分析 78 4.5 模型應用場景之實用性觀察 79 第五章 結論與建議 82 5.1 結論 82 5.2 建議 83 參考文獻 85 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 水位量測 | zh_TW |
| dc.subject | 影像辨識 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | HRNet | zh_TW |
| dc.subject | 虛擬水尺 | zh_TW |
| dc.subject | deep learning | en |
| dc.subject | image recognition | en |
| dc.subject | water level measurement | en |
| dc.subject | virtual gauge | en |
| dc.subject | HRNet | en |
| dc.title | 應用HRNet模型建立自動水位量測系統 | zh_TW |
| dc.title | Application of the HRNet Model to Automated Water Level Measurement | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 韓仁毓;甯方璽 | zh_TW |
| dc.contributor.oralexamcommittee | Jen-Yu Han;Fang-Shii Ning | en |
| dc.subject.keyword | 水位量測,虛擬水尺,HRNet,深度學習,影像辨識, | zh_TW |
| dc.subject.keyword | water level measurement,virtual gauge,HRNet,deep learning,image recognition, | en |
| dc.relation.page | 91 | - |
| dc.identifier.doi | 10.6342/NTU202504228 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-08-13 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 土木工程學系 | - |
| dc.date.embargo-lift | 2025-08-19 | - |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf | 66.86 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。